A Cross-Residual Learning for Image Recognition

TL;DR

This paper introduces C-ResNets, a variant of ResNets with enhanced information interaction and reduced computation, achieving comparable accuracy while saving GPU resources across multiple image recognition datasets.

Contribution

The paper proposes C-ResNets, a new cross-residual network architecture that reduces parameters and computation while maintaining classification performance.

Findings

C-ResNets match ResNet accuracy on multiple datasets.

C-ResNets significantly reduce GPU computation and memory usage.

C-ResNets are practical alternatives to ResNets in resource-constrained scenarios.

Abstract

ResNets and its variants play an important role in various fields of image recognition. This paper gives another variant of ResNets, a kind of cross-residual learning networks called C-ResNets, which has less computation and parameters than ResNets. C-ResNets increases the information interaction between modules by densifying jumpers and enriches the role of jumpers. In addition, some meticulous designs on jumpers and channels counts can further reduce the resource consumption of C-ResNets and increase its classification performance. In order to test the effectiveness of C-ResNets, we use the same hyperparameter settings as fine-tuned ResNets in the experiments. We test our C-ResNets on datasets MNIST, FashionMnist, CIFAR-10, CIFAR-100, CALTECH-101 and SVHN. Compared with fine-tuned ResNets, C-ResNets not only maintains the classification performance, but also enormously reduces the amount of calculations and parameters which greatly save the utilization rate of GPUs and GPU memory resources. Therefore, our C-ResNets is competitive and viable alternatives to ResNets in various scenarios. Code is available at https://github.com/liangjunhello/C-ResNet